© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 25057
    Prev
    Next
    INDEX
    Explanations

    references to college sports, particularly soccer

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    gated
    Context Size
    1,024
    Dataset
    Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĺµ
    -0.17
     Sir
    -0.15
    apl
    -0.15
     Charlottesville
    -0.15
     Rice
    -0.15
     Garage
    -0.15
    òn
    -0.14
    prompt
    -0.14
    ayet
    -0.14
    Sir
    -0.14
    POSITIVE LOGITS
    annis
    0.17
    ifar
    0.16
    ouncer
    0.15
     Hayward
    0.15
    iyim
    0.15
    âĶĺ
    0.15
    keterangan
    0.14
    *)_
    0.14
     célib
    0.14
    WER
    0.14
    Activations Density 0.008%

    No Known Activations